293 citations · 789 across the 14 of their papers we have counts for
15 papers
Multilingual Document-Level Translation Enables Zero-Shot Transfer From Sentences to Documents
Biao Zhang, Ankur Bapna, Melvin Johnson +3
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of pa…
Sentence Boundary Augmentation For Neural Machine Translation Robustness
Daniel Li, Te I, Naveen Arivazhagan +2
Neural Machine Translation (NMT) models have demonstrated strong state of the art performance on translation tasks where well-formed training and evaluation data are provided, but…
Language-agnostic BERT Sentence Embedding
Fangxiaoyu Feng, Yinfei Yang, Daniel Cer +2
While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning (Reimers and Gurevych, 2019), BERT base…
Leveraging Monolingual Data with Self-Supervision for Multilingual Neural Machine Translation
Aditya Siddhant, Ankur Bapna, Yuan Cao +5
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to i…
Re-translation versus Streaming for Simultaneous Translation
Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey +1
There has been great progress in improving streaming machine translation, a simultaneous paradigm where the system appends to a growing hypothesis as more source content becomes av…
Controlling Computation versus Quality for Neural Sequence Models
Ankur Bapna, Naveen Arivazhagan, Orhan Firat
Most neural networks utilize the same amount of compute for every example independent of the inherent complexity of the input. Further, methods that adapt the amount of computation…
Re-Translation Strategies For Long Form, Simultaneous, Spoken Language Translation
Naveen Arivazhagan, Colin Cherry, Te I +3
We investigate the problem of simultaneous machine translation of long-form speech content. We target a continuous speech-to-text scenario, generating translated captions for a liv…
Simple, Scalable Adaptation for Neural Machine Translation
Ankur Bapna, Naveen Arivazhagan, Orhan Firat
Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maint…
Investigating Multilingual NMT Representations at Scale
Sneha Reddy Kudugunta, Ankur Bapna, Isaac Caswell +2
Multilingual Neural Machine Translation (NMT) models have yielded large empirical success in transfer learning settings. However, these black-box representations are poorly underst…
Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation
Aditya Siddhant, Melvin Johnson, Henry Tsai +5
The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a sin…
Small and Practical BERT Models for Sequence Labeling
Henry Tsai, Jason Riesa, Melvin Johnson +3
We propose a practical scheme to train a single multilingual sequence labeling model that yields state of the art results and is small and fast enough to run on a single CPU. Start…
Massively Multilingual Neural Machine Translation in the Wild: Findings and Challenges
Naveen Arivazhagan, Ankur Bapna, Orhan Firat +10
We introduce our efforts towards building a universal neural machine translation (NMT) system capable of translating between any language pair. We set a milestone towards this goal…
Monotonic Infinite Lookback Attention for Simultaneous Machine Translation
Naveen Arivazhagan, Colin Cherry, Wolfgang Macherey +5
Simultaneous machine translation begins to translate each source sentence before the source speaker is finished speaking, with applications to live and streaming scenarios. Simulta…
The Missing Ingredient in Zero-Shot Neural Machine Translation
Naveen Arivazhagan, Ankur Bapna, Orhan Firat +3
Multilingual Neural Machine Translation (NMT) models are capable of translating between multiple source and target languages. Despite various approaches to train such models, they…
Neural Language Correction with Character-Based Attention
Ziang Xie, Anand Avati, Naveen Arivazhagan +2
Natural language correction has the potential to help language learners improve their writing skills. While approaches with separate classifiers for different error types have high…